Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    tracking performance and progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ного
    0.97
    ный
    0.95
    ные
    0.83
    шения
    0.79
    కు
    0.74
    ný
    0.73
    the
    0.72
    вається
    0.70
    ков
    0.69
    ujourd
    0.69
    POSITIVE LOGITS
     Track
    0.88
     for
    0.82
     attribu
    0.77
     ट्रैक
    0.76
     TRACK
    0.72
     track
    0.72
     averages
    0.71
     H
    0.71
     monitors
    0.71
     distribu
    0.71
    Act Density 0.009%

    No Known Activations